• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.6
• /
• pp.591-596
• /
• 2019

In this paper, we implemented a deep learning operation structure with less influence of local PC performance. In general, the deep learning model has a large amount of computation and is heavily influenced by the performance of the processing PC. In this paper, we implemented deep learning operation using AWS and streaming server to reduce this limitation. First, deep learning operations were performed on AWS so that deep learning operation would work even if the performance of the local PC decreased. However, with AWS, the output is less real-time relative to the input when computed. Second, we use streaming server to increase the real-time of deep learning model. If the streaming server is not used, the real-time performance is poor because the images must be processed one by one or by stacking the images. We used the YOLO v3 model as a deep learning model for performance comparison experiments, and compared the performance of local PCs with instances of AWS and GTX1080, a high-performance GPU. The simulation results show that the test time per image is 0.023444 seconds when using the p3 instance of AWS, which is similar to the test time per image of 0.027099 seconds on a local PC with the high-performance GPU GTX1080.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.23 no.6
• /
• pp.734-743
• /
• 1999

The local Nusselt numbers have been measured for a round turbulent jet impinging on the concave surface with and without rib. Liquid crystal/transient method was used to determine the Nusselt number distributions along the surface. The temperature on the surface was measured using liquid crystal and a digital color image processing system. The experiments were made for the jet Reynolds number (Re) 23,000, the dimensionless nozzle-to-surface distance (L/d) from 4 to 10, the dimensionless surface curvature (d/D) 0.056, and the rib type (height ($d_1$) 0.2 cm, pitch (p) from 1.2 to 3.2 cm). It was founded that only when $L/d{\geq}6$, the average Nusselt numbers on the concave surface with rib are higher than those without rib, mainly due to an increase in the turbulent intensity caused by the effect of rib attached to the wall surface. It was realized that the rib attached to the concave surface may no longer enhance the heat transfer rate or even lowers it depending on the rib type and flow conditions. In addition, the results by the steady-state method using the gold-film Intrex were in good agreement with those by the transient shroud method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.6
• /
• pp.867-873
• /
• 2018

Recently, interests in the field of image processing have increased with the increased demand for digital imaging devices. However, digital images are damaged by the noise generated by various causes during image processing. Generally in digital imaging devices, noise such as AWGN, etc. is generated and performance and reliability are deteriorated, and various researches are in progress to remove it. Accordingly in the present paper, an algorithm to protect the high frequency components of the images and to efficiently remove AWGN is proposed. The proposed algorithm calculates the final output by adjusting estimate values applied with Gaussian mask and weight values applied according to the local mask distribution. And for performance evaluation of the proposed algorithm, simulations were performed with the existing methods, and the characteristics were compared through PSNR and the processed, enlarged images.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.661-663
• /
• 2016

Corruption occurs in the process of processing image signal and the corruption changes the pixel value within the image to damage the original information. AWGN(additive white Gaussian noise) is a representative example. For filters to remove AWGN, there are filters such as MF(mean filter), WF(wiener filter), and AWMF(adaptive weighted mean filter). However images processed through standard previous filters lock preservation characteristics in edge areas. Therefore, threshold value is applied for processing on the standard deviation of the local mask in this study and if the standard deviation is smaller than the threshold value, it is not filtered and if the value is bigger than the threshold value, the study suggested an algorithm that processes using weighted value utilizing standard deviation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.343-345
• /
• 2017

In digital era image processing has been utilized in a variety of media such as TV, camera and smart phone. However, in the process of analyzing, recognizing, and processing image data, deterioration occurs due to various causes and Salt & Pepper noise occurs. Typical methods for removing such noise include SMF, CWMF, and SWMF. However, existing methods have a somewhat poor noise canceling characteristic in Salt & Pepper noise environment. Therefore, in this paper, we propose an algorithm to remove Salt & Pepper noise effectively by using bilinear interpolation method and median filter according to noise density of local mask. And using the PSNR(Peak Signal to Noise Ratio) it compared to the existing methods and their performance in order to determine the performance of the proposed method.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.12
• /
• pp.519-524
• /
• 2023

In hashing-based image retrieval, the hash code of a manipulated image is different from the original image, making it difficult to search for the same image. This paper proposes and evaluates a self-supervised deephashing model that generates perceptual hash codes from feature information such as texture, shape, and color of images. The comparison models are autoencoder-based variational inference models, but the encoder is designed with a fully connected layer, convolutional neural network, and transformer modules. The proposed model is a variational inference model that includes a SimAM module of extracting geometric patterns and positional relationships within images. The SimAM module can learn latent vectors highlighting objects or local regions through an energy function using the activation values of neurons and surrounding neurons. The proposed method is a representation learning model that can generate low-dimensional latent vectors from high-dimensional input images, and the latent vectors are binarized into distinguishable hash code. From the experimental results on public datasets such as CIFAR-10, ImageNet, and NUS-WIDE, the proposed model is superior to the comparative model and analyzed to have equivalent performance to the supervised learning-based deephashing model. The proposed model can be used in application systems that require low-dimensional representation of images, such as image search or copyright image determination.

• Cartoon and Animation Studies
• /
• s.40
• /
• pp.243-260
• /
• 2015

Being a symbolic image to let traditional 'mother wonlee' contents characters known widely, need to be made in a way that can deliver the powerful message of korea An-dong traditional local contents and the value of regent story. As for the contents character develope methods and the scope of the study, an theoretical study was conducted based on literature review, and, factor plus fiction field surveys, and the legend story and then an effect of character marketing on global contents with original identity. 'mother wonlee' pre-production plaining have been analysis with creative described based on the ancients features and the classification of ancient original characters, and the situation and the concept of An-dong local place. as a results this thesis is show up how to make up a main character develop processing and make a features design processing of the characters who different age and a scenes. as a conclusion is drawing about a 'Wonlee' and 'Eungtea' both main Character plaining processing and graphics; traditional face, all clothes, body proportion, etc. Also we trade to traditional patten with character planing. it will be a high value industry which facilitates a variety of industries in conjunction with marketing traditional source characters in global. Recognizing the value of traditional story main character design and graphics marketing and utilizing the value through various media will create infinite value, enabling the global marketing.

• The KIPS Transactions:PartA
• /
• v.14A no.2
• /
• pp.77-84
• /
• 2007

The intima media thickness(IMT) of the carotid artery from B mode ultrasound images has recently been proposed as the most useful index of individual atherosclerosis and can be used to predict major cardiovascular events. Ultrasonic measurements of the IMT are conventionally obtained by manually tracing interfaces between tissue layers. The drawbacks of this method are the inter and intra observer variability and its inefficiency. In this paper, we present a multiresolution snake method combined with the dynamic programming, which overcomes the various noises and sensitivity to initialization of conventional snake. First, an image pyramid is constructed using the Gaussian pyramid that maintains global edge information with smoothing in the images, and then the boundaries are automatically detected in the lowest resolution level by minimizing a cost function based on dynamic programming. The cost function includes cost terms which are representing image features and geometrical continuity of the vessel interfaces. Since the detected boundaries are selected as initial contour of the snake for the next level, this automated approach solves the problem of the initialization. Moreover, the proposed snake improves the problem of converging th the local minima by defining the external energy based on multiple image features. In this paper, our method has been validated by computing the correlation between manual and automatic measurements. This automated detection method has obtained more accurate and reproducible results than conventional edge detection by considering multiple image features.

• Journal of the Korea Computer Industry Society
• /
• v.3 no.9
• /
• pp.1145-1156
• /
• 2002

A method to measure the speed and distance of moving object is proposed using the stereo vision system. One of the most important factors for measuring the speed and distance of moving object is the accuracy of object tracking. Accordingly, the background image algorithm is adopted to track the rapidly moving object and the local opening operator algorithm is used to remove the shadow and noise of object. The extraction efficiency of moving object is improved by using the adaptive threshold algorithm independent to variation of brightness. Since the left and right central points are compensated, the more exact speed and distance of object can be measured. Using the background image algorithm and local opening operator algorithm, the computational processes are reduced and it is possible to achieve the real-time processing of the speed and distance of moving object. The simulation results show that background image algorithm can track the moving object more rapidly than any other algorithm. The application of adaptive threshold algorithm improved the extraction efficiency of the target by reducing the candidate areas. Since the central point of the target is compensated by using the binocular parallax, the error of measurement for the speed and distance of moving object is reduced. The error rate of measurement for the distance from the stereo camera to moving object and for the speed of moving object are 2.68% and 3.32%, respectively.

• Journal of Digital Convergence
• /
• v.19 no.11
• /
• pp.75-83
• /
• 2021

This study presented the analysis results and implications by identifying the structural relationship between the image of food tourism products, the long-term orientation of attachment, and the behavioral intention. The convenience sampling method of the non-probability sampling method was used, and the survey was conducted non-face-to-face due to COVID-19. This study was conducted for customers who live in Jeollabuk-do and Jeollanam-do and have experienced local traditional food. As for the survey method, the main researcher's acquaintances and related experts were consulted and utilized to select the survey subjects, and the survey was conducted by sending/returning them by mail or e-mail. Statistical processing was analyzed using SPSS 25.0 and AMOS 25.0 statistical packages. As a result of the verification, the relationship between the image and attachment of food tourism, the relationship between the long-term orientation in the attachment of traditional food, and the behavioral intention in the attachment of traditional food are significant. A significant positive (+) relationship was formed in the relationship of hypothesis setting according to the research purpose of the relationship.